Learning optimal control policies directly on physical systems is challenging. Even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during exploration are limited to local optima. This work proposes GoSafeOpt as the first provably safe and optimal algorithm that can safely discover globally optimal policies for systems with high-dimensional state space. We demonstrate the superiority of GoSafeOpt over competing model-free safe learning methods in simulation and hardware experiments on a robot arm.

Access hardware results here and software results here. The paper is available here.